# ProgResViT: Progressive Resolution and Width for Adaptive Vision Transformers

arXiv: https://arxiv.org/abs/2609.03216 · HTML: https://mlsanity.com/paper/2609.03216/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 30 of 31)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [DynaBERT: Dynamic BERT with Adaptive Width and Depth](https://mlsanity.com/paper/2004.04037/) (2020)
- [FlexiViT: One Model for All Patch Sizes](https://mlsanity.com/paper/2212.08013/) (2022)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [CF-ViT: A General Coarse-to-Fine Method for Vision Transformer](https://mlsanity.com/paper/2203.03821/) (2022)
- [Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity](https://mlsanity.com/paper/2406.14479/) (2024)
- [ResFormer: Scaling ViTs with Multi-Resolution Training](https://mlsanity.com/paper/2212.00776/) (2022)
- [ViTAR: Vision Transformer with Any Resolution](https://mlsanity.com/paper/2403.18361/) (2024)
- [MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers](https://mlsanity.com/paper/2307.02321/) (2023)
- [Block-Recurrent Dynamics in Vision Transformers](https://mlsanity.com/paper/2512.19941/) (2025)
- [LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition](https://mlsanity.com/paper/2402.00033/) (2024)
- [MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation](https://mlsanity.com/paper/2112.11542/) (2021)
- [HydraViT: Stacking Heads for a Scalable ViT](https://mlsanity.com/paper/2409.17978/) (2024)
- [Multi-Tailed Vision Transformer for Efficient Inference](https://mlsanity.com/paper/2203.01587/) (2022)
- [Attention Is All You Need For Mixture-of-Depths Routing](https://mlsanity.com/paper/2412.20875/) (2024)
- [ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference](https://mlsanity.com/paper/2507.10800/) (2025)

## Abstract (arXiv)

Vision Transformers (ViTs) typically process every image using a fixed input resolution and model width, even though many images can be classified with substantially less computation. We introduce ProgResViT, an input-adaptive ViT that performs inference progressively across multiple rounds. The first round processes a low-resolution image with a narrow subnetwork. Inference terminates when the prediction is sufficiently confident; otherwise, the model reuses the representations produced in the current round and proceeds with a higher-resolution input and a wider subnetwork to refine its prediction. As all rounds share a single backbone, we propose Progress-Conditioned Soft Gating (PSG), which conditions token fusion and layer outputs on the current round, block, and input resolution. On image classification, applying ProgResViT to DeiT yields better accuracy-compute trade-offs than adaptive-width, adaptive-depth, and dynamic-token baselines. With knowledge distillation, a DeiT-based ProgResViT achieves 84.9% top-1 accuracy, slightly exceeding the reported DeiT-III-S accuracy under a comparable evaluation setting. We show that the same design also provides favorable accuracy-compute trade-offs for self-supervised DINO representations and downstream semantic segmentation. Code is available at https://github.com/ds-kiel/ProgResViT.